hadiqa123
/

xlsr_ur_training

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

hadiqa123 commited on Sep 3, 2022

Commit

30d6e3e

•

1 Parent(s): bfb3a27

add tokenizer

Files changed (4) hide show

added_tokens.json +4 -0
special_tokens_map.json +16 -0
tokenizer_config.json +2 -0
vocab.json +56 -53

added_tokens.json ADDED Viewed

	@@ -0,0 +1,4 @@

+{
+  "</s>": 59,
+  "<s>": 58
+}

special_tokens_map.json CHANGED Viewed

@@ -1,4 +1,20 @@
 {
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

 {
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "[PAD]",

tokenizer_config.json CHANGED Viewed

@@ -2,8 +2,10 @@
   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

   "bos_token": "<s>",
   "do_lower_case": false,
   "eos_token": "</s>",
+  "name_or_path": "./",
   "pad_token": "[PAD]",
   "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
   "tokenizer_class": "Wav2Vec2CTCTokenizer",
   "unk_token": "[UNK]",
   "word_delimiter_token": "|"

vocab.json CHANGED Viewed

@@ -1,57 +1,60 @@
 {
-  "'": 25,
-  "[PAD]": 54,
-  "[UNK]": 53,
-  "|": 9,
-  "؟": 36,
-  "ء": 16,
-  "آ": 40,
-  "ؤ": 46,
-  "ئ": 27,
-  "ا": 44,
-  "ب": 17,
-  "ت": 50,
-  "ث": 20,
-  "ج": 51,
-  "ح": 31,
-  "خ": 7,
-  "د": 33,
-  "ذ": 28,
-  "ر": 10,
-  "ز": 14,
-  "س": 2,
-  "ش": 18,
-  "ص": 13,
-  "ض": 19,
-  "ط": 34,
-  "ظ": 22,
-  "ع": 32,
-  "غ": 37,
-  "ف": 8,
-  "ق": 42,
-  "ل": 5,
   "م": 29,
-  "ن": 4,
-  "و": 49,
-  "ي": 38,
-  "ُ": 21,
-  "ِ": 1,
-  "ّ": 15,
-  "ٔ": 11,
-  "ٰ": 39,
-  "ٹ": 47,
-  "پ": 30,
   "چ": 43,
-  "ڈ": 6,
-  "ڑ": 23,
-  "ژ": 12,
-  "ک": 0,
-  "گ": 52,
-  "ں": 24,
-  "ھ": 48,
-  "ہ": 3,
-  "ۂ": 45,
-  "ی": 35,
-  "ے": 41,
-  "۔": 26
 }

 {
+  "[PAD]": 57,
+  "[UNK]": 56,
+  "|": 0,
+  "،": 1,
+  "؟": 2,
+  "ء": 3,
+  "آ": 4,
+  "ؤ": 5,
+  "ئ": 6,
+  "ا": 7,
+  "ب": 8,
+  "ت": 9,
+  "ث": 10,
+  "ج": 11,
+  "ح": 12,
+  "خ": 13,
+  "د": 14,
+  "ذ": 15,
+  "ر": 16,
+  "ز": 17,
+  "س": 18,
+  "ش": 19,
+  "ص": 20,
+  "ض": 21,
+  "ط": 22,
+  "ظ": 23,
+  "ع": 24,
+  "غ": 25,
+  "ف": 26,
+  "ق": 27,
+  "ل": 28,
   "م": 29,
+  "ن": 30,
+  "و": 31,
+  "ى": 32,
+  "ي": 33,
+  "ً": 34,
+  "ُ": 35,
+  "ِ": 36,
+  "ّ": 37,
+  "ٓ": 38,
+  "ٔ": 39,
+  "ٰ": 40,
+  "ٹ": 41,
+  "پ": 42,
   "چ": 43,
+  "ڈ": 44,
+  "ڑ": 45,
+  "ژ": 46,
+  "ک": 47,
+  "گ": 48,
+  "ں": 49,
+  "ھ": 50,
+  "ہ": 51,
+  "ۂ": 52,
+  "ی": 53,
+  "ے": 54,
+  "۔": 55
 }